Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
Jianing Yang, Alexander Sax, Kevin J. Liang, Mikael Henaff, Hao Tang, Ang Cao, Joyce Chai, Franziska Meier
Abstract
Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a fundamentally pairwise approach, processing images in pairs and necessitating costly global alignment procedures to reconstruct from multiple views. In this work, we propose Fast 3D Reconstruction (Fast3R), a novel multi-view generalization to DUSt3R that achieves efficient and scalable 3D reconstruction by processing many views in parallel. Fast3R's Transformer-based architecture forwards N images in a single forward pass, bypassing the need for iterative alignment. Through extensive experiments on camera pose estimation and 3D reconstruction, Fast3R demonstrates state-of-the-art performance, with significant improvements in inference speed and reduced error accumulation. These results establish Fast3R as a robust alternative for multi-view applications, offering enhanced scalability without compromising reconstruction accuracy. Project website: https://fast3r-3d.github.io
BibTeX
@InProceedings{Yang_2025_CVPR,
author = {Yang, Jianing and Sax, Alexander and Liang, Kevin J. and Henaff, Mikael and Tang, Hao and Cao, Ang and Chai, Joyce and Meier, Franziska and Feiszli, Matt},
title = {Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {21924-21935}
}